M2 Max 96GB vs RTX 4070

For running local LLMs · 4 reports across 2 models

Side A

Vendor: apple
VRAM: 96GB
Memory: Unified

Side B

Vendor: nvidia
VRAM: 12GB
Memory: Discrete

Tokens per second by model

Model	M2 Max 96GB	RTX 4070
Gemma 4up to 31B	—	55.0n=2
Qwen3.6up to 35B	28.0n=2	—

More comparisons